信息公告: 《热带气象学报》再次入选“中国科学引文数据库(CSCD)来源期刊”以及连续8次入编《中文核心期刊要目总览》    
引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 10次   下载 12 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于机器学习的目标点雷电安全风险预警方法研究
殷启元1,2, 林蟒3, 杨思鹏4, 朱怡颖1,2, 方俏娴1, 杜晖1, 周方聪2
1.广东省气候中心,广东广州510641;2.海南省南海气象防灾减灾重点实验室,海南海口571000;3.海珠区气象局,广东广州510220;4.中国气象局广州热带海洋气象研究所,广东广州510641
摘要:
收集广东地区1404组包括四个预警类型历史雷暴过程数据样本。结合目标点周围雷电发生的物理特征、雷电灾害的孕灾环境和承灾体特征的7个预报因子,利用四种机器学习算法训练得到面向目标点的雷电安全风险分级预警模型,并开展多指标对各模型进行评价分析,发现无等级模型和四级等级模型中都是随机森林算法的预警准确率最好,分别是95%和73%,而传统的卷积神经网络模型效果不佳。并选取广州塔作为目标点进行模型验证方法可行性,最终得到适应于广东雷暴特征的雷电安全风险预警分级模型。同时,根据本研究过程中可能存在不足提出下一步优化升级思路和方法。
关键词:  雷电  雷电安全  风险预警  机器学习
DOI:10.16032/j.issn.1004-4965.2024.021
分类号:
基金项目:
Target Point Lightning Safety Risk Early Warning Based on Machine Learning
YIN Qiyuan1,2, LIN Mang3, YANG Sipeng4, ZHU Yiying1,2, FANG Qiaoxian1, DU Hui1, ZHOU Fangcong2
1.Guangdong Climate Center ,Guangzhou 510641 ,China;2.Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province , Haikou 571000 ,China;3.Meteorological Office of Haizhu District ,Guangzhou 510220 ,China;4.Guangzhou Institute of Tropical and Marine Meteorology ,CMA ,Guangzhou 510641 ,China
Abstract:
The present study aimed to develop an accurate lightning risk classification and warning model for target points by using 1404 sets of data from four types of historical thunderstorm processes in Guangdong .Four machine learning algorithms were employed ,and seven forecast factors ,such as the physical characteristics of lightning occurrence around the target point ,the breeding environment of lightning hazard ,and the characteristics of the disaster-bearing body ,were adopted to conduct multi-index evaluation and analysis of each risk early warning model .The results showed that the random forest algorithm exhibited the highest early warning accuracy in both the no-level model (95%)and the four-level model (73%).In contrast ,the traditional convolutional neural network model proved to be ineffective for this purpose .Canton Tower was selected as the target point for model feasibility verification ,and a lightning safety risk warning grading model tailored to the characteristics of thunderstorms in Guangdong was obtained .Finally ,based on the identified deficiencies in the research process ,ideas and methods for future optimization were proposed .
Key words:  lightning  lightning safety  risk warning  machine learning
版权所有《热带气象学报》编辑部 您是第8017109位访问者
Tel:020-39456476、39456435 E-mail:LLSH@gd121.cn
技术支持:本系统由北京勤云科技发展有限公司设计